Predicting bank inactivity: A comparative analysis of machine learning techniques for imbalanced data

Ali Ben Mrad, Amine Lahiani (), Salma Mefteh-Wali and Nada Mselmi ()
Additional contact information
Ali Ben Mrad: Qassim University [Kingdom of Saudi Arabia], جامعة صفاقس - Université de Sfax - University of Sfax
Amine Lahiani: LEO - Laboratoire d'Économie d'Orleans [2022-...] - UO - Université d'Orléans - UT - Université de Tours - UCA - Université Clermont Auvergne, GUST - Gulf University for Science and Technology, South Ural State University, Chelyabinsk, Russia.
Salma Mefteh-Wali: ESSCA - ESSCA – École supérieure des sciences commerciales d'Angers = ESSCA Business School
Nada Mselmi: RITM - Réseaux Innovation Territoires et Mondialisation - Université Paris-Saclay

Post-Print from HAL

Abstract: This study compares the predictive accuracy of a set of machine learning models coupled with three resampling techniques (Random Undersampling, Random Oversampling, and Synthetic Minority Oversampling Technique) in predicting bank inactivity. Our sample includes listed banks in EU-28 member states between 2011 and 2019. We employed 23 financial ratios comprising capital adequacy, asset quality, management capability, earnings, liquidity, and sensitivity indicators. The empirical findings established that XGBoost performs exceptionally well as a classifier in predicting bank inactivity, particularly when considering a one-year time frame before the event. Furthermore, our findings indicate that random forest with Synthetic Minority Oversampling Technique demonstrates the highest predictive accuracy two years prior to inactivity, while XGBoost with Random Oversampling outperforms other methods three years in advance. Furthermore, the empirical results emphasize the significance of management capability and loan quality ratios as key factors in predicting bank inactivity. Our findings present important policy implications.

Date: 2024-05-09
References: Add references at CitEc
Citations:

Published in Annals of Operations Research, 2024, 351, pp.937-963. ⟨10.1007/s10479-024-06018-0⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04797802

DOI: 10.1007/s10479-024-06018-0

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().